© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 56158
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to job application materials and professional documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /the
    -0.07
    ÑıÑĤ
    -0.06
     Bölüm
    -0.06
    785
    -0.06
    DrawerToggle
    -0.06
    ervers
    -0.06
    uger
    -0.05
    ãĥ¼ãĥ³
    -0.05
    guarded
    -0.05
    wis
    -0.05
    POSITIVE LOGITS
     template
    0.08
     examples
    0.08
    _TEMPLATE
    0.07
    Template
    0.07
     templates
    0.07
    imson
    0.07
    .template
    0.07
    æºĸ
    0.07
    tlement
    0.07
    BoxLayout
    0.07
    Activations Density 0.009%

    No Known Activations